Hy-MT2-1.8B vs Mistral Small 4
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Hy-MT2-1.8B is 3.4× cheaper than Mistral Small 4 on a typical 3:1 input/output mix. Mistral Small 4 has the larger context window (262K vs 8K).
| Hy-MT2-1.8B | Mistral Small 4 | |
|---|---|---|
| Input price / 1M | $0.044 | $0.15 |
| Output price / 1M | $0.18 | $0.60 |
| Blended price (3:1) | $0.0772 | $0.26 |
| Cached input / 1M | — | $0.015 |
| Context window | 8K | 262K |
| Max output | 4K | 210K |
| Intelligence index | — | 11.3 |
| Coding index | — | 26.6 |
| Providers | 1 | 3 |
| Best provider uptime (30m) | 100.0% | 100.0% |
| Vision input | No | Yes |
| Reasoning | No | Yes |
| Tool calling | No | Yes |
| Released | 2026-08-20 | 2026-03-16 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, Hy-MT2-1.8B or Mistral Small 4?
Hy-MT2-1.8B is 3.4× cheaper than Mistral Small 4 on a typical 3:1 input/output mix.
Hy-MT2-1.8B vs Mistral Small 4: which has a bigger context window?
Hy-MT2-1.8B: 8,192 tokens. Mistral Small 4: 262,144 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: Hy-MT2-1.8B ≈ $176.50, Mistral Small 4 ≈ $600.00.
More comparisons
Hy-MT2-1.8B vs GLM 5.3 PrimeHy-MT2-1.8B vs Qwen3.8 Max PrimeHy-MT2-1.8B vs Command A+Hy-MT2-1.8B vs GPT-6 Luna ProHy-MT2-1.8B vs GPT-6 LunaHy-MT2-1.8B vs GPT-6 Sol ProHy-MT2-1.8B vs GPT-6 SolHy-MT2-1.8B vs Claude Opus 5.5Hy-MT2-1.8B vs MiMo-V2.6-Pro-UltraSpeedHy-MT2-1.8B vs MiMo-V2.6-FlashHy-MT2-1.8B vs Grok 4.7Hy-MT2-1.8B vs Qwen3.8 Omni FlashHy-MT2-1.8B vs GLM 5.3 FlashXHy-MT2-1.8B vs DeepSeek V4.1 FlashHy-MT2-1.8B vs GPT-6 AstraHy-MT2-1.8B vs GPT-6 Astra ProMistral Small 4 vs GLM 5.3 PrimeMistral Small 4 vs Qwen3.8 Max PrimeMistral Small 4 vs Command A+Mistral Small 4 vs GPT-6 Luna ProMistral Small 4 vs GPT-6 LunaMistral Small 4 vs GPT-6 Sol ProMistral Small 4 vs GPT-6 SolMistral Small 4 vs Claude Opus 5.5